AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

Guan'an Wang, Tianzhu Zhang, Jian Cheng, Si Liu, Yang Yang, Zengguang Hou

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 603 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add pixel alignment module (ablation)Basel. · SYSU-MM01 all-search single-shotRank-1 (%): 29.6 -> 40.6Improved
add feature alignment module (ablation)Basel. · SYSU-MM01 all-search single-shotRank-1 (%): 29.6 -> 34.1Improved
add pixel alignment module (ablation)Basel. · SYSU-MM01 all-search single-shotmAP (%): 33.0 -> 38.7Improved
add feature alignment module (ablation)Basel. · SYSU-MM01 all-search single-shotmAP (%): 33.0 -> 36.2Improved
use pixel alignment instead of feature alignment (ablation)FeatAlign · SYSU-MM01 all-search single-shotRank-1 (%): 34.1 -> 40.6Improved
stack pixel and feature alignment with two separate discriminators (ablation)PixAlign · SYSU-MM01 all-search single-shotRank-1 (%): 40.6 -> 36.2Hurt
replace two separate discriminators with the joint discriminator (ablation)AlignGAN- · SYSU-MM01 all-search single-shotRank-1 (%): 36.2 -> 42.4Improved
add joint discriminator on top of feature alignment only (ablation)FeatAlign · SYSU-MM01 all-search single-shotRank-1 (%): 34.1 -> 42.4Improved
use AlignGAN instead of cmGANcmGAN · SYSU-MM01 all-search single-shotRank-1 (%): 27.0 -> 42.4Improved
use AlignGAN instead of cmGANcmGAN · SYSU-MM01 indoor-search single-shotRank-1 (%): 31.7 -> 45.9Improved
use AlignGAN instead of D-HSMED-HSME · RegDB thermal2visibleRank-1 (%): 50.2 -> 56.3Improved
use AlignGAN instead of D-HSMED-HSME · RegDB visible2thermalRank-1 (%): 50.9 -> 57.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy